Particle Data Platform

RL Is "Sucking Through A Straw"

40:4642:50 · 124s

Karpathy unloads on reinforcement learning, calling it noisy, inefficient and coining the line that it’s like “sucking supervision through a straw.”

We value your privacy

We use cookies to understand how you use our platform and to improve your experience. Click "Accept All" to consent, or "Decline non-essential" to opt out of non-essential cookies. Read our Privacy Policy.